Proxy Indicators for the Quality of Open-domain Dialogues
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Authors
The automatic evaluation of open-domain dialogues remains a largely unsolved challenge. Thus, despite the abundance of work done in the field, human judges have to evaluate dialogues' quality. As a consequence, performing such evaluations at scale is usually expensive. This work investigates using a deep-learning model trained on the General Language Understanding Evaluation (GLUE) benchmark to serve as a quality indication of open-domain dialogues. The aim is to use the various GLUE tasks as different perspectives on judging the quality of conversation, thus reducing the need for additional training data or responses that serve as quality references. Due to this nature, the method can infer various quality metrics and derive a component-based overall score. We achieve statistically significant correlation coefficients of up to 0.7.
Original language | English |
---|---|
Title of host publication | EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings |
Editors | Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih |
Number of pages | 22 |
Publisher | Association for Computational Linguistics (ACL) |
Publication date | 01.01.2021 |
Pages | 7834-7855 |
ISBN (electronic) | 9781955917094 |
DOIs | |
Publication status | Published - 01.01.2021 |
Externally published | Yes |
Event | 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 - ONLINE, Punta Cana, Dominican Republic Duration: 07.11.2021 → 11.11.2021 https://2021.emnlp.org |
Bibliographical note
Funding Information:
Turning to Maintains Context, we see the inverse perspective. The pair-wise sentence proxy indicators applied to the dialogue context, and target response demonstrate the best ability, while the single sentence is the worst. Furthermore, the observation is partially supported by the pair-wise tasks applied to the dialogue facts.
Publisher Copyright:
© 2021 Association for Computational Linguistics
- Informatics
- Business informatics